Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    certain formatting cues or syntactic structures in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     occurred
    -0.60
     utilizing
    -0.59
     Utilizing
    -0.59
     planification
    -0.58
     behaviors
    -0.58
    isShow
    -0.55
    MessageOf
    -0.54
     tradisional
    -0.54
    behaviors
    -0.53
    TestingModule
    -0.53
    POSITIVE LOGITS
     flak
    0.67
    APORE
    0.67
    הערות
    0.66
     lenker
    0.64
     yore
    0.61
    eabouts
    0.60
    AllAfrica
    0.60
    IsMutable
    0.59
     vouch
    0.59
     freilich
    0.59
    Act Density 0.170%

    No Known Activations